Doctoral Thesis: End-to-end Learning for Robust Decision Making

Alexander Amini

Abstract:
Because the physical world is complex, ambiguous, and unpredictable, autonomous agents must be engineered to exhibit a human-level degree of flexibility and generality — far beyond what we are capable of explicitly programming. Such realizations of autonomy are capable of not only reliably solving a particular problem, but also anticipating what could go wrong in order to strategize, adapt, and continuously learn. Achieving such rich and intricate decision making requires rethinking the foundations of intelligence across all stages of the autonomous learning lifecycle.

In this thesis, we develop new learning-based approaches towards dynamic, resilient, and robust decision making of autonomous systems. We advance robust decision making in the wild by addressing critical challenges that arise at all stages, stemming from the data used for training, to the models that learn on this data, to the algorithms to reliably adapt to unexpected events during deployment. We start by exploring how we can computationally design rich, synthetic environments capable of simulating a continuum of hard to collect, out-of-distribution edge-cases, amenable for use during both training and evaluation. Taking this rich data foundation, we then create efficient, expressive learning models together with the algorithms necessary to optimize their representations and overcome imbalances in under-represented and challenging data. Finally, with our trained models, we then turn to the deployment setting where we should still anticipate that our system will be faced with entirely new scenarios that they have never encountered during training. To this end, we develop adaptive and uncertainty-aware algorithms for estimating model uncertainty, and exploiting it’s presence to realize generalizable decision making, even in the presence of unexpected events.

Details

• Date: Thursday, April 21
• Time: 9:00 am
• Location: MIT Kiva Conference Room (32-G449)

Additional Location Details:

Signup to receive Zoom link: https://forms.gle/aihJbVgPygUDXXrp8

Thesis Committee: Daniela Rus, Pulkit Agrawal, Sertac Karaman, John Leonard

Bio:
Alexander Amini is a PhD student at the Massachusetts Institute of Technology (MIT), in the Computer Science and Artificial Intelligence Laboratory (CSAIL), with Prof. Daniela Rus. His research focuses on developing the science and engineering of autonomy and its applications to safe decision making for autonomous agents. His work has spanned learning end-to-end control (i.e., perception-to-actuation) of autonomous systems, formulating confidence of neural networks, mathematical modeling of human mobility, as well as building complex inertial refinement systems. In addition to research, Amini is the lead organizer and lecturer for MIT 6.S191: Introduction to Deep Learning, MIT’s official introductory course on deep learning. Amini is a recipient of the NSF Graduate Research Fellowship and completed his Bachelor of Science (B.S.) and Master of Science (M.S.) in Electrical Engineering and Computer Science at MIT, with a minor in Mathematics. More details are available at www.mit.edu/~amini